© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 14320
    Prev
    Next
    INDEX
    Explanations

    pink terror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    爌
    0.56
    <0xA4>
    0.51
    成為
    0.49
    מס
    0.48
    çı
    0.47
    與
    0.47
    ર
    0.46
    द्या
    0.46
     ち
    0.45
    தி
    0.45
    POSITIVE LOGITS
     UML
    0.45
     Cinderella
    0.45
     h
    0.45
     volgens
    0.43
     klass
    0.43
     richt
    0.41
     Naval
    0.41
     finesse
    0.41
     RSI
    0.41
     Murder
    0.40
    Activations Density 0.011%

    No Known Activations